diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 474eb8c66feeb2c98de2f5d6fe1db84de752c806..05c4aa00cc862e3b1dad1b344b0eddb9d6f44db4 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -7,6 +7,7 @@ struct x86_mapping_info {
unsigned long page_flag; /* page flag for PMD or PUD entry */
unsigned long offset; /* ident mapping offset */
bool direct_gbpages; /* PUD level 1GB page support */
+ unsigned long kernpg_flag; /* kernel pagetable flag override */
};
int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 70ef205489f00e53ff568180c4dcbf6fb9e6ded1..e8183acf931faf7ec4cc444de386f9db826ec952 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -207,6 +207,14 @@ struct kexec_entry64_regs {
uint64_t r15;
uint64_t rip;
};
+
+extern int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages,
+ gfp_t gfp);
+#define arch_kexec_post_alloc_pages arch_kexec_post_alloc_pages
+
+extern void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages);
+#define arch_kexec_pre_free_pages arch_kexec_pre_free_pages
+
#endif
typedef void crash_vmclear_fn(void);
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 32095af0fefb904cc87737e1d6ea4217531937cb..830992fc5a069937e6cc6f4c83d59e3afd599df4 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -213,6 +213,7 @@ enum page_cache_mode {
#define PAGE_KERNEL __pgprot(__PAGE_KERNEL | _PAGE_ENC)
#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO | _PAGE_ENC)
#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC | _PAGE_ENC)
+#define PAGE_KERNEL_EXEC_NOENC __pgprot(__PAGE_KERNEL_EXEC)
#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX | _PAGE_ENC)
#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE | _PAGE_ENC)
#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE | _PAGE_ENC)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index cb0a30473c2310b76695c73ec6fad3cd1e7b051f..9cf8daacc0469ca1644eb7da98f762b7c58f88de 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -87,7 +87,7 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
}
pte = pte_offset_kernel(pmd, vaddr);
- set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
+ set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC_NOENC));
return 0;
err:
free_transition_pgtable(image);
@@ -115,6 +115,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
.alloc_pgt_page = alloc_pgt_page,
.context = image,
.page_flag = __PAGE_KERNEL_LARGE_EXEC,
+ .kernpg_flag = _KERNPG_TABLE_NOENC,
};
unsigned long mstart, mend;
pgd_t *level4p;
@@ -602,3 +603,22 @@ void arch_kexec_unprotect_crashkres(void)
{
kexec_mark_crashkres(false);
}
+
+int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp)
+{
+ /*
+ * If SME is active we need to be sure that kexec pages are
+ * not encrypted because when we boot to the new kernel the
+ * pages won't be accessed encrypted (initially).
+ */
+ return set_memory_decrypted((unsigned long)vaddr, pages);
+}
+
+void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages)
+{
+ /*
+ * If SME is active we need to reset the pages back to being
+ * an encrypted mapping before freeing them.
+ */
+ set_memory_encrypted((unsigned long)vaddr, pages);
+}
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3ca198080ea9294486ae9a1121e7815dfba7cb19..bd6b85fac66696da70e316656ad6f0d51291f8aa 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -355,6 +355,7 @@ bool xen_set_default_idle(void)
return ret;
}
#endif
+
void stop_this_cpu(void *dummy)
{
local_irq_disable();
@@ -365,8 +366,20 @@ void stop_this_cpu(void *dummy)
disable_local_APIC();
mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
- for (;;)
- halt();
+ for (;;) {
+ /*
+ * Use wbinvd followed by hlt to stop the processor. This
+ * provides support for kexec on a processor that supports
+ * SME. With kexec, going from SME inactive to SME active
+ * requires clearing cache entries so that addresses without
+ * the encryption bit set don't corrupt the same physical
+ * address that has the encryption bit set when caches are
+ * flushed. To achieve this a wbinvd is performed followed by
+ * a hlt. Even if the processor is not in the kexec/SME
+ * scenario this only adds a wbinvd to a halting processor.
+ */
+ asm volatile("wbinvd; hlt" : : : "memory");
+ }
}
/*
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index adab1595f4bd89ba0729db70dd21d619d93e829d..31cea988fa36c5571687d1e18e2d5c914271b0f8 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -51,7 +51,7 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
if (!pmd)
return -ENOMEM;
ident_pmd_init(info, pmd, addr, next);
- set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+ set_pud(pud, __pud(__pa(pmd) | info->kernpg_flag));
}
return 0;
@@ -79,7 +79,7 @@ static int ident_p4d_init(struct x86_mapping_info *info, p4d_t *p4d_page,
if (!pud)
return -ENOMEM;
ident_pud_init(info, pud, addr, next);
- set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
+ set_p4d(p4d, __p4d(__pa(pud) | info->kernpg_flag));
}
return 0;
@@ -93,6 +93,10 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
unsigned long next;
int result;
+ /* Set the default pagetable flags if not supplied */
+ if (!info->kernpg_flag)
+ info->kernpg_flag = _KERNPG_TABLE;
+
for (; addr < end; addr = next) {
pgd_t *pgd = pgd_page + pgd_index(addr);
p4d_t *p4d;
@@ -116,14 +120,14 @@ int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
if (result)
return result;
if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
- set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
+ set_pgd(pgd, __pgd(__pa(p4d) | info->kernpg_flag));
} else {
/*
* With p4d folded, pgd is equal to p4d.
* The pgd entry has to point to the pud page table in this case.
*/
pud_t *pud = pud_offset(p4d, 0);
- set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+ set_pgd(pgd, __pgd(__pa(pud) | info->kernpg_flag));
}
}
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index dd056fab9e35c958c7aee14156e1df5640fb2556..2b7590f5483a1fc4474fbecddd099977222531cb 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -327,6 +327,14 @@ static inline void *boot_phys_to_virt(unsigned long entry)
return phys_to_virt(boot_phys_to_phys(entry));
}
+#ifndef arch_kexec_post_alloc_pages
+static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, gfp_t gfp) { return 0; }
+#endif
+
+#ifndef arch_kexec_pre_free_pages
+static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { }
+#endif
+
#else /* !CONFIG_KEXEC_CORE */
struct pt_regs;
struct task_struct;
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 1ae7c41c33c19c54e4b08d33c0c59da78244efba..20fef1a38602d9d0ed6fdb5d359d5604fbafc3dd 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -301,7 +301,7 @@ static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
{
struct page *pages;
- pages = alloc_pages(gfp_mask, order);
+ pages = alloc_pages(gfp_mask & ~__GFP_ZERO, order);
if (pages) {
unsigned int count, i;
@@ -310,6 +310,13 @@ static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
count = 1 << order;
for (i = 0; i < count; i++)
SetPageReserved(pages + i);
+
+ arch_kexec_post_alloc_pages(page_address(pages), count,
+ gfp_mask);
+
+ if (gfp_mask & __GFP_ZERO)
+ for (i = 0; i < count; i++)
+ clear_highpage(pages + i);
}
return pages;
@@ -321,6 +328,9 @@ static void kimage_free_pages(struct page *page)
order = page_private(page);
count = 1 << order;
+
+ arch_kexec_pre_free_pages(page_address(page), count);
+
for (i = 0; i < count; i++)
ClearPageReserved(page + i);
__free_pages(page, order);